]>
Commit | Line | Data |
---|---|---|
8244288d | 1 | # coding: utf-8 |
e7916255 | 2 | from __future__ import unicode_literals |
8244288d | 3 | |
99afb3dd JMF |
4 | import re |
5 | ||
6 | from .common import InfoExtractor | |
c5f51551 | 7 | from ..compat import compat_str |
86916dae S |
8 | from ..utils import ( |
9 | ExtractorError, | |
10 | unified_strdate, | |
c5f51551 | 11 | HEADRequest, |
57ce8a6d | 12 | int_or_none, |
86916dae | 13 | ) |
99afb3dd JMF |
14 | |
15 | ||
16 | class WatIE(InfoExtractor): | |
c5f51551 | 17 | _VALID_URL = r'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)' |
99afb3dd | 18 | IE_NAME = 'wat.tv' |
c28df247 S |
19 | _TESTS = [ |
20 | { | |
21 | 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html', | |
c5f51551 | 22 | 'md5': '83d882d9de5c9d97f0bb2c6273cde56a', |
c28df247 S |
23 | 'info_dict': { |
24 | 'id': '11713067', | |
c28df247 S |
25 | 'ext': 'mp4', |
26 | 'title': 'Soupe de figues à l\'orange et aux épices', | |
27 | 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.', | |
28 | 'upload_date': '20140819', | |
29 | 'duration': 120, | |
30 | }, | |
31 | }, | |
32 | { | |
33 | 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html', | |
57ce8a6d | 34 | 'md5': '34bdfa5ca9fd3c7eb88601b635b0424c', |
c28df247 S |
35 | 'info_dict': { |
36 | 'id': '11713075', | |
c28df247 S |
37 | 'ext': 'mp4', |
38 | 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)', | |
c28df247 | 39 | 'upload_date': '20140816', |
c28df247 | 40 | }, |
57ce8a6d | 41 | 'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."], |
fa800269 | 42 | }, |
c28df247 | 43 | ] |
e7916255 | 44 | |
57ce8a6d RA |
45 | _FORMATS = ( |
46 | (200, 416, 234), | |
47 | (400, 480, 270), | |
48 | (600, 640, 360), | |
49 | (1200, 640, 360), | |
50 | (1800, 960, 540), | |
51 | (2500, 1280, 720), | |
52 | ) | |
53 | ||
99afb3dd | 54 | def _real_extract(self, url): |
c5f51551 | 55 | video_id = self._match_id(url) |
56 | video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36)) | |
8244288d | 57 | |
c5f51551 | 58 | # 'contentv4' is used in the website, but it also returns the related |
59 | # videos, we don't need them | |
57ce8a6d RA |
60 | video_data = self._download_json( |
61 | 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id) | |
62 | video_info = video_data['media'] | |
a54bda3a | 63 | |
86916dae S |
64 | error_desc = video_info.get('error_desc') |
65 | if error_desc: | |
57ce8a6d RA |
66 | self.report_warning( |
67 | '%s returned error: %s' % (self.IE_NAME, error_desc)) | |
86916dae | 68 | |
8244288d | 69 | chapters = video_info['chapters'] |
57ce8a6d RA |
70 | if chapters: |
71 | first_chapter = chapters[0] | |
99afb3dd | 72 | |
57ce8a6d RA |
73 | def video_id_for_chapter(chapter): |
74 | return chapter['tc_start'].split('-')[0] | |
8244288d | 75 | |
57ce8a6d RA |
76 | if video_id_for_chapter(first_chapter) != video_id: |
77 | self.to_screen('Multipart video detected') | |
78 | entries = [self.url_result('wat:%s' % video_id_for_chapter(chapter)) for chapter in chapters] | |
79 | return self.playlist_result(entries, video_id, video_info['title']) | |
80 | # Otherwise we can continue and extract just one part, we have to use | |
81 | # the video id for getting the video url | |
82 | else: | |
83 | first_chapter = video_info | |
c5f51551 | 84 | |
57ce8a6d | 85 | title = first_chapter['title'] |
c5f51551 | 86 | |
87 | def extract_url(path_template, url_type): | |
88 | req_url = 'http://www.wat.tv/get/%s' % (path_template % video_id) | |
89 | head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type) | |
90 | red_url = head.geturl() | |
91 | if req_url == red_url: | |
92 | raise ExtractorError( | |
93 | '%s said: Sorry, this video is not available from your country.' % self.IE_NAME, | |
94 | expected=True) | |
95 | return red_url | |
96 | ||
c5f51551 | 97 | formats = [] |
57ce8a6d RA |
98 | try: |
99 | http_url = extract_url('android5/%s.mp4', 'http') | |
100 | m3u8_url = extract_url('ipad/%s.m3u8', 'm3u8') | |
101 | m3u8_formats = self._extract_m3u8_formats( | |
102 | m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls') | |
103 | formats.extend(m3u8_formats) | |
104 | formats.extend(self._extract_f4m_formats( | |
105 | m3u8_url.replace('ios.', 'web.').replace('.m3u8', '.f4m'), | |
106 | video_id, f4m_id='hds', fatal=False)) | |
107 | for m3u8_format in m3u8_formats: | |
108 | vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr') | |
109 | if not vbr or not abr: | |
110 | continue | |
111 | format_id = m3u8_format['format_id'].replace('hls', 'http') | |
112 | fmt_url = re.sub(r'%s-\d+00-\d+' % video_id, '%s-%d00-%d' % (video_id, round(vbr / 100), round(abr)), http_url) | |
113 | if self._is_valid_url(fmt_url, video_id, format_id): | |
114 | f = m3u8_format.copy() | |
115 | f.update({ | |
116 | 'url': fmt_url, | |
117 | 'format_id': format_id, | |
118 | 'protocol': 'http', | |
119 | }) | |
120 | formats.append(f) | |
121 | self._sort_formats(formats) | |
122 | except ExtractorError: | |
123 | abr = 64 | |
124 | for vbr, width, height in self._FORMATS: | |
125 | tbr = vbr + abr | |
126 | format_id = 'http-%s' % tbr | |
127 | fmt_url = 'http://dnl.adv.tf1.fr/2/USP-0x0/%s/%s/%s/ssm/%s-%s-64k.mp4' % (video_id[-4:-2], video_id[-2:], video_id, video_id, vbr) | |
128 | if self._is_valid_url(fmt_url, video_id, format_id): | |
129 | formats.append({ | |
130 | 'format_id': format_id, | |
131 | 'url': fmt_url, | |
132 | 'vbr': vbr, | |
133 | 'abr': abr, | |
134 | 'width': width, | |
135 | 'height': height, | |
136 | }) | |
137 | ||
138 | date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4') | |
139 | upload_date = unified_strdate(date_diffusion) if date_diffusion else None | |
140 | duration = None | |
141 | files = video_info['files'] | |
142 | if files: | |
143 | duration = int_or_none(files[0].get('duration')) | |
a54bda3a | 144 | |
e7916255 | 145 | return { |
c5f51551 | 146 | 'id': video_id, |
57ce8a6d RA |
147 | 'title': title, |
148 | 'thumbnail': first_chapter.get('preview'), | |
149 | 'description': first_chapter.get('description'), | |
150 | 'view_count': int_or_none(video_info.get('views')), | |
e7916255 | 151 | 'upload_date': upload_date, |
57ce8a6d | 152 | 'duration': duration, |
a54bda3a | 153 | 'formats': formats, |
e7916255 | 154 | } |